jandres/GenAIExamples
1
0
Fork 0
Code Issues Pull Requests Actions 3 Packages Projects Releases Wiki Activity

Align parameters for "max_token, repetition_penalty,presence_penalty,frequency_penalty" (#726)

Browse Source 
Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
This commit is contained in:
XinyaoWa
2024-09-19 14:15:25 +08:00
committed by GitHub
parent 372d78c2ac
commit 2f03a3a894
24 changed files with 111 additions and 73 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
AudioQnA/docker_compose/intel/cpu/xeon/README.md
View File

@@ -108,7 +108,7 @@ curl http://${host_ip}:3006/generate \
# llm microservice
curl http://${host_ip}:3007/v1/chat/completions\
-X POST \
-d '{"query":"What is Deep Learning?","max_new_tokens":17,"top_k":10,"top_p":0.95,"typical_p":0.95,"temperature":0.01,"repetition_penalty":1.03,"streaming":false}' \
-d '{"query":"What is Deep Learning?","max_tokens":17,"top_k":10,"top_p":0.95,"typical_p":0.95,"temperature":0.01,"repetition_penalty":1.03,"streaming":false}' \
-H 'Content-Type: application/json'
# speecht5 service

2
AudioQnA/docker_compose/intel/hpu/gaudi/README.md
View File

@@ -108,7 +108,7 @@ curl http://${host_ip}:3006/generate \
# llm microservice
curl http://${host_ip}:3007/v1/chat/completions\
-X POST \
-d '{"query":"What is Deep Learning?","max_new_tokens":17,"top_k":10,"top_p":0.95,"typical_p":0.95,"temperature":0.01,"repetition_penalty":1.03,"streaming":false}' \
-d '{"query":"What is Deep Learning?","max_tokens":17,"top_k":10,"top_p":0.95,"typical_p":0.95,"temperature":0.01,"repetition_penalty":1.03,"streaming":false}' \
-H 'Content-Type: application/json'
# speecht5 service

2
AudioQnA/tests/test_gmc_on_gaudi.sh
View File

@@ -34,7 +34,7 @@ function validate_audioqa() {
export CLIENT_POD=$(kubectl get pod -n $APP_NAMESPACE -l app=client-test -o jsonpath={.items..metadata.name})
echo "$CLIENT_POD"
accessUrl=$(kubectl get gmc -n $APP_NAMESPACE -o jsonpath="{.items[?(@.metadata.name=='audioqa')].status.accessUrl}")
byte_str=$(kubectl exec "$CLIENT_POD" -n $APP_NAMESPACE -- curl $accessUrl -s -X POST -d '{"byte_str": "UklGRigAAABXQVZFZm10IBIAAAABAAEARKwAAIhYAQACABAAAABkYXRhAgAAAAEA", "parameters":{"max_new_tokens":64, "do_sample": true, "streaming":false}}' -H 'Content-Type: application/json' | jq .byte_str)
byte_str=$(kubectl exec "$CLIENT_POD" -n $APP_NAMESPACE -- curl $accessUrl -s -X POST -d '{"byte_str": "UklGRigAAABXQVZFZm10IBIAAAABAAEARKwAAIhYAQACABAAAABkYXRhAgAAAAEA", "parameters":{"max_tokens":64, "do_sample": true, "streaming":false}}' -H 'Content-Type: application/json' | jq .byte_str)
echo "$byte_str" > $LOG_PATH/curl_audioqa.log
if [ -z "$byte_str" ]; then
echo "audioqa failed, please check the logs in ${LOG_PATH}!"

2
AudioQnA/tests/test_gmc_on_xeon.sh
View File

@@ -34,7 +34,7 @@ function validate_audioqa() {
export CLIENT_POD=$(kubectl get pod -n $APP_NAMESPACE -l app=client-test -o jsonpath={.items..metadata.name})
echo "$CLIENT_POD"
accessUrl=$(kubectl get gmc -n $APP_NAMESPACE -o jsonpath="{.items[?(@.metadata.name=='audioqa')].status.accessUrl}")
byte_str=$(kubectl exec "$CLIENT_POD" -n $APP_NAMESPACE -- curl $accessUrl -s -X POST -d '{"byte_str": "UklGRigAAABXQVZFZm10IBIAAAABAAEARKwAAIhYAQACABAAAABkYXRhAgAAAAEA", "parameters":{"max_new_tokens":64, "do_sample": true, "streaming":false}}' -H 'Content-Type: application/json' | jq .byte_str)
byte_str=$(kubectl exec "$CLIENT_POD" -n $APP_NAMESPACE -- curl $accessUrl -s -X POST -d '{"byte_str": "UklGRigAAABXQVZFZm10IBIAAAABAAEARKwAAIhYAQACABAAAABkYXRhAgAAAAEA", "parameters":{"max_tokens":64, "do_sample": true, "streaming":false}}' -H 'Content-Type: application/json' | jq .byte_str)
echo "$byte_str" > $LOG_PATH/curl_audioqa.log
if [ -z "$byte_str" ]; then
echo "audioqa failed, please check the logs in ${LOG_PATH}!"